{"slug": "codex-users-hit-tool-call-and-workspace-bugs-on-the-new-gpt-5-6-build", "title": "Codex Users Hit Tool-Call and Workspace Bugs on the New GPT-5.6 Build", "summary": "Codex users are reporting three critical bugs in the new GPT-5.6 build, including a tool-call namespace collision that causes valid tool calls to be rejected, a missing workspace tools issue on the Codex Desktop that leaves agents blind, and a rollout gap where users cannot access the model. The bugs highlight that the new model family is shipping faster than the tool-wiring and entitlement plumbing, risking agent reliability.", "body_md": "The rollout of the GPT-5.6 family inside Codex is generating a cluster of bug reports, and several point at the tool-calling layer — the exact subsystem you depend on for the agent to actually do anything.\n\nThe sharpest is a **high-priority** report of a ToolName namespace collision. On `gpt-5.6-sol`\n\n, the agent emits a tool call that collides with an existing one and surfaces as `unsupported custom tool call: execexec`\n\n. The label says it is a CLI tool-calls bug. The practical effect: a capability the model reaches for gets rejected, so the task stalls or degrades to a weaker path. Namespace collisions like this are easy to introduce when a new model version adds tools whose names overlap with custom ones you registered — and they are annoying precisely because the model \"thinks\" it called something valid.\n\nA second report: on the GPT-5.6 Codex Desktop, **new tasks can start without workspace tools**. If the file and shell tools are not attached at task start, the agent is effectively blind and handcuffed until something reconnects them — and the user may not realize why the first few turns went nowhere. The label ties it to Windows and the app surface.\n\nThe third is simpler but just as real: a user reports **not having GPT-5.6 available on a personal cloud workstation** despite expecting it. That is a rollout/entitlement gap — the model the marketing talks about is not the model your account can reach, which makes any \"try the new build\" instruction a dead end.\n\nThree bugs, one theme: the new model family is shipping faster than the tool-wiring and entitlement plumbing around it. If you are on Codex and planning to lean on GPT-5.6, verify your workspace tools attach and your account actually has the model before you trust a session. The [Claude Code data-loss writeup](https://dev.to/blog/claude-code-sonnet-5-deletes-folders/) is a reminder that model-version bumps are exactly when agent reliability regresses — watch the tool layer first.", "url": "https://wpnews.pro/news/codex-users-hit-tool-call-and-workspace-bugs-on-the-new-gpt-5-6-build", "canonical_source": "https://dev.to/terminalblog/codex-users-hit-tool-call-and-workspace-bugs-on-the-new-gpt-56-build-3n60", "published_at": "2026-07-11 16:22:28+00:00", "updated_at": "2026-07-11 16:44:04.131083+00:00", "lang": "en", "topics": ["large-language-models", "ai-agents", "ai-products", "developer-tools"], "entities": ["Codex", "GPT-5.6", "Claude Code"], "alternates": {"html": "https://wpnews.pro/news/codex-users-hit-tool-call-and-workspace-bugs-on-the-new-gpt-5-6-build", "markdown": "https://wpnews.pro/news/codex-users-hit-tool-call-and-workspace-bugs-on-the-new-gpt-5-6-build.md", "text": "https://wpnews.pro/news/codex-users-hit-tool-call-and-workspace-bugs-on-the-new-gpt-5-6-build.txt", "jsonld": "https://wpnews.pro/news/codex-users-hit-tool-call-and-workspace-bugs-on-the-new-gpt-5-6-build.jsonld"}}